X-Git-Url: http://git.vpit.fr/?a=blobdiff_plain;f=lib%2FRegexp%2FWildcards.pm;h=15b42c79fccf5f0b8122a5db5938bc2d846e1eb0;hb=0acfe1e394d884c4ff93c844467c446873681c24;hp=abb59f0fefde1543312419d3a3a3f4cca5205a63;hpb=a86792e2f3991cbfdda962a94f851bfb44e9ed8e;p=perl%2Fmodules%2FRegexp-Wildcards.git diff --git a/lib/Regexp/Wildcards.pm b/lib/Regexp/Wildcards.pm index abb59f0..15b42c7 100644 --- a/lib/Regexp/Wildcards.pm +++ b/lib/Regexp/Wildcards.pm @@ -3,8 +3,9 @@ package Regexp::Wildcards; use strict; use warnings; -use Carp qw/croak/; -use Text::Balanced qw/extract_bracketed/; +use Carp qw; +use Scalar::Util qw; +use Text::Balanced qw; =head1 NAME @@ -12,13 +13,13 @@ Regexp::Wildcards - Converts wildcard expressions to Perl regular expressions. =head1 VERSION -Version 1.02 +Version 1.03 =cut -use vars qw/$VERSION/; +use vars qw<$VERSION>; BEGIN { - $VERSION = '1.02'; + $VERSION = '1.03'; } =head1 SYNOPSIS @@ -34,12 +35,12 @@ BEGIN { $re = $rw->convert('%a_c%', 'sql'); # Turn SQL wildcards into regexps. $rw = Regexp::Wildcards->new( - do => [ qw/jokers brackets/ ], # Do jokers and brackets. - capture => [ qw/any greedy/ ], # Capture *'s greedily. + do => [ qw ], # Do jokers and brackets. + capture => [ qw ], # Capture *'s greedily. ); $rw->do(add => 'groups'); # Don't escape groups. - $rw->capture(rem => [ qw/greedy/ ]); # Actually we want non-greedy matches. + $rw->capture(rem => [ qw ]); # Actually we want non-greedy matches. $re = $rw->convert('*a{,(b)?}?c*'); # '(.*?)a(?:|(b).).c(.*?)' $rw->capture(); # No more captures. @@ -61,24 +62,24 @@ Typesets that mimic the behaviour of Windows and Unix shells are also provided. sub _check_self { croak 'First argument isn\'t a valid ' . __PACKAGE__ . ' object' - unless ref $_[0] and $_[0]->isa(__PACKAGE__); + unless blessed $_[0] and $_[0]->isa(__PACKAGE__); } my %types = ( - jokers => [ qw/jokers/ ], - sql => [ qw/sql/ ], - commas => [ qw/commas/ ], - brackets => [ qw/brackets/ ], - unix => [ qw/jokers brackets/ ], - win32 => [ qw/jokers commas/ ], + jokers => [ qw ], + sql => [ qw ], + commas => [ qw ], + brackets => [ qw ], + unix => [ qw ], + win32 => [ qw ], ); -$types{$_} = $types{win32} for qw/dos os2 MSWin32 cygwin/; -$types{$_} = $types{unix} for qw/linux +$types{$_} = $types{win32} for qw; +$types{$_} = $types{unix} for qw; my %escapes = ( jokers => '?*', @@ -115,7 +116,7 @@ sub _validate { } my %checked; - for (qw/set add rem/) { + for (qw) { my $opt = $opts{$_}; next unless defined $opt; my $cb = { @@ -230,27 +231,35 @@ They fit into six classes : =item * -C<'jokers'> converts C to C<.> and C<*> to C<.*> ; +C<'jokers'> + +Converts C to C<.> and C<*> to C<.*>. 'a**\\*b??\\?c' ==> 'a.*\\*b..\\?c' =item * -C<'sql'> converts C<_> to C<.> and C<%> to C<.*> ; +C<'sql'> + +Converts C<_> to C<.> and C<%> to C<.*>. 'a%%\\%b__\\_c' ==> 'a.*\\%b..\\_c' =item * -C<'commas'> converts all C<,> to C<|> and puts the complete resulting regular expression inside C<(?: ... )> ; +C<'commas'> + +Converts all C<,> to C<|> and puts the complete resulting regular expression inside C<(?: ... )>. 'a,b{c,d},e' ==> '(?:a|b\\{c|d\\}|e)' =item * -C<'brackets'> converts all matching C<{ ... , ... }> brackets to C<(?: ... | ... )> alternations. +C<'brackets'> + +Converts all matching C<{ ... , ... }> brackets to C<(?: ... | ... )> alternations. If some brackets are unbalanced, it tries to substitute as many of them as possible, and then escape the remaining unmatched C<{> and C<}>. -Commas outside of any bracket-delimited block are also escaped ; +Commas outside of any bracket-delimited block are also escaped. 'a,b{c,d},e' ==> 'a\\,b(?:c|d)\\,e' '{a\\{b,c}d,e}' ==> '(?:a\\{b|c)d\\,e\\}' @@ -258,14 +267,18 @@ Commas outside of any bracket-delimited block are also escaped ; =item * -C<'groups'> keeps the parenthesis C<( ... )> of the original string without escaping them. +C<'groups'> + +Keeps the parenthesis C<( ... )> of the original string without escaping them. Currently, no check is done to ensure that the parenthesis are matching. 'a(b(c))d\\(\\)' ==> (no change) =item * -C<'anchors'> prevents the I C<^> and I C<$> anchors to be escaped. +C<'anchors'> + +Prevents the I C<^> and I C<$> anchors to be escaped. Since C<[...]> character class are currently escaped, a C<^> will always be interpreted as I. 'a^b$c' ==> (no change) @@ -298,7 +311,7 @@ No argument means C<< set => [ ] >>. $rw->do(set => 'jokers'); # Only translate jokers. $rw->do('jokers'); # Same. - $rw->do(add => [ qw/sql commas/ ]); # Translate also SQL and commas. + $rw->do(add => [ qw ]); # Translate also SQL and commas. $rw->do(rem => 'jokers'); # Specifying both 'sql' and 'jokers' is useless. $rw->do(); # Translate nothing. @@ -366,28 +379,36 @@ This method works like L, except that the classes are different : =item * -C<'single'> will capture all unescaped I<"exactly one"> metacharacters, i.e. C for wildcards or C<_> for SQL ; +C<'single'> + +Captures all unescaped I<"exactly one"> metacharacters, i.e. C for wildcards or C<_> for SQL. 'a???b\\??' ==> 'a(.)(.)(.)b\\?(.)' 'a___b\\__' ==> 'a(.)(.)(.)b\\_(.)' =item * -C<'any'> will capture all unescaped I<"any"> metacharacters, i.e. C<*> for wildcards or C<%> for SQL ; +C<'any'> + +Captures all unescaped I<"any"> metacharacters, i.e. C<*> for wildcards or C<%> for SQL. 'a***b\\**' ==> 'a(.*)b\\*(.*)' 'a%%%b\\%%' ==> 'a(.*)b\\%(.*)' =item * -C<'greedy'>, when used in conjunction with C<'any'>, will make the C<'any'> captures greedy (by default they are not) ; +C<'greedy'> + +When used in conjunction with C<'any'>, it makes the C<'any'> captures greedy (by default they are not). 'a***b\\**' ==> 'a(.*?)b\\*(.*?)' 'a%%%b\\%%' ==> 'a(.*?)b\\%(.*?)' =item * -C<'brackets'> will capture matching C<{ ... , ... }> alternations. +C<'brackets'> + +Capture matching C<{ ... , ... }> alternations. 'a{b\\},\\{c}' ==> 'a(b\\}|\\{c)' @@ -395,7 +416,7 @@ C<'brackets'> will capture matching C<{ ... , ... }> alternations. $rw->capture(set => 'single'); # Only capture "exactly one" metacharacters. $rw->capture('single'); # Same. - $rw->capture(add => [ qw/any greedy/ ]); # Also greedily capture "any" metacharacters. + $rw->capture(add => [ qw ]); # Also greedily capture "any" metacharacters. $rw->capture(rem => 'greedy'); # No more greed please. $rw->capture(); # Capture nothing. @@ -448,7 +469,7 @@ An object module shouldn't export any function, and so does this one. =head1 DEPENDENCIES -L (core module since perl 5), L (since 5.7.3). +L (core module since perl 5), L, L (since 5.7.3). =head1 CAVEATS @@ -479,7 +500,7 @@ Tests code coverage report is available at L